The Top Ten Myths of SC

By Andrew Jones

November 11, 2011

SC11, the world’s greatest yearly supercomputing show rolls into Seattle this week. To help prepare you for the big week, we have put together a list of the top 10 myths of the phenomenon that is SC. With a little discussion of each, hopefully we will bring out the good, the bad, the hopes and realities of SC. And, maybe, along the way we’ll see why SC matters so much to our community.

Myth 1: It’s all partying

Yes, it’s true, there are lots of networking receptions, meetings-over-a-drink, and business dinners held during the week of SC. Perhaps even one or two events that struggle to be described as anything other than a party. But hold on before you dismiss SC as merely a week of parties with a conference somewhere in the background. There will be several thousand attendees, over a hundred technical sessions, around 300 exhibition booths, and hundreds of hours of meetings held in the surrounding hotels and venues.

Before the exhibition has its grand opening on Monday evening, hundreds of staff from exhibiting organizations will have been working hard over the weekend to setup booths and demos. Lots of people will also have been attending tutorials, workshops, vendor meetings, and private business meetings over the weekend. So, for many attending SC11, Monday night is halfway into the week – not the first day – and a desire to wind down with a drink and friends is only fair.

Likewise, each day, people will have had to endure hours standing on booths sustaining extreme enthusiasm for their products, or sitting through slide decks that oscillate between no useful detail and far too much detail, or searching the exhibition or technical program for a solution to a problem they’re not sure they have yet. A sponsored social gathering is a good way to relax after all that – or to engage with more contacts if you are still feeling workaholic.

Myth 2: HPC center directors wander the exhibition floor with $100m to spend

Although every salesperson attending SC dreams of the big opportunity arriving from a casual encounter on the booth, I would bet that most people with $100m to spend have booked up a series of meetings with potential suppliers. After all, if you had given somebody that much money to spend, you’d hope they had a better procurement plan than to simply wander about the exhibit hall looking for a shiny toy that caught their attention?

Of course, in most cases, the supercomputer center directors don’t have the money to spend – government funding agencies have money to spend, supercomputer centers just help them spend it! Some government funding agencies use specialist advisors (like NAG or other independent consultants) to scout the market at SC to inform and plan for big procurements. In most cases, a competitive procurement process will actually spend the money – although meetings with vendors at SC are often used to support that process. But it is very rare that the $100m check is signed or announced at SC itself.

Myth 3: Industrial users of HPC have money to spend on every latest software gadget

It’s a popular hope of anyone selling products and solutions – especially in the niche software space. Especially those who think their niche is the answer to a perceived industry wide problem. Or those in the academic sector, who, against the challenges of sustaining software in the academic funding environment, turn in hope to industry as a promised land of plenty. Industry has untapped reserves of money. Or not.

Often users of HPC in industry are focused in small groups within companies and have operating budgets that would make national labs and academics cringe. Investing in software in industry can be a cultural and funding “adventure” too. The difference (to paint the extremes of the picture) is that the academic reward and funding system is determined to invest in new methods and implementations wherever possible (“research”) and avoid re-use or ongoing evolution, whereas the common industrial environment is determined to avoid investing in new software or major re-developments unless re-use or evolution is overpoweringly ineffective.

I have made these extremes with artistic license, but they serve the point – balance in speculation and stability is required – and software strategy is usually key to that balance in HPC.

Myth 4: Everyone knows everyone

Don’t be silly. It’s often said – I say it too – “supercomputing is a small community”. The extension, “everyone knows everyone” is stretching the credibility though, with several thousand attendees at SC11. But, there is a large degree of interconnection in the supercomputing community and so the community often feels close and small. Within the overall HPC world, there are a significant number of people who are very active and meet many times a year between SCs.

However, focusing only on those high profile members of the HPC world would be detrimental to the overall SC11 audience – many of whom will be new to HPC or on the peripherals of the traditional HPC community. SC must – and does – support all parts of the potential HPC community – new entrants, established centers, high profile researchers, and observers considering how HPC can help them. SC11 is a very social and friendly event for those who are seasoned HPC professionals – but we must make sure those who have poked a tentative toe in the water feel welcome and not overwhelmed.

Myth 5: SC week is the best time to issue a press release

Yes, it is. In the same sense that the best place to exhibit a tree is in the forest. You’d better have an impressive tree compared to the others – otherwise it’s just a tree with all detail forgotten. Each year, SC brings forth a flood of press releases, case studies, and so on. The only advantage to issuing your press release during SC itself is that, briefly, some of the core IT and even mainstream media spare some attention for supercomputing, so if you hit lucky you get a wider audience than normally.

But most press releases will simply be another small bubble in the seething froth of news frenzy that surrounds SC11 week. Plus, so many of your potential audience will be too busy creating their own news or standing on booths or in meetings to read anyone else’s news. Unless it’s big news of course. SC is a great time to spread and collect rumors though. Much more fun than factual press releases 🙂

Myth 6: You can sustain 30+ meetings in a week and still be paying attention to that roadmap detail presentation on the last day

Do I really need to explain that one? See my SC11 diary series for what goes into some people’s SC11 planning. By Thursday afternoon’s presentation, vendor A’s plans to bring out widget B in 2019 with a feature of C=1.00234 rather than someone else’s 1.00235 is hard to focus on, compared to the impending flight home.

Myth 7: The technical program is the most important part of SC11

Not if you have $100m to spend on a supercomputer! Best to walk the show floor 🙂 or book some meetings with potential suppliers and your favorite HPC consultants. Joking aside, the technical program is actually very important. The competition for papers at SC is intense, which is promising for quality, plus there is a wide range of tutorials and workshops. Thus, there are excellent opportunities to catch up on the latest advances in HPC, learn new skills or disseminate your work.

But even the most academically focused attendee should never ignore the other two key parts of SC – the exhibition and the social/networking events. The exhibition can often provide as many gems of innovation as the technical program. Collaborations are sparked by conversations on the exhibition floor or at the social events.

Myth 8: The exhibition is the most important part of SC11

The exhibition can be a hive of activity – at its peak (Monday night’s grand opening) easily the most vibrant single event of the show, in my opinion beating even the technical program keynotes. The exhibition can also feel like a ghost town at times, with seemingly the only people in the vast hall those who have drawn booth duty.

Most of the time it is somewhere between the two, a steady stream of punters drifting or hurrying along the carpets, with eager booth personnel trying to woo them with logo’d giveaways, sweet smiles, or entrapping questions. But, as above, the exhibition is only one of the three important parts of SC – and the technical program and social events are just as important.

Myth 9: The whole HPC world will be at SC

Much as the organizers would like everyone associated with buying, using, selling or researching HPC products, technologies and services to attend, that is not the reality. As I wrote on my blog recently, there are many people for whom HPC is an essential part of their work or toolset, but is not an end in itself and thus SC is not a core event for them. Even within the community of HPC practitioners or researchers, many cannot attend SC every year.

But, against that, a huge proportion of the active HPC world will be at SC11 – most organizations providing HPC technologies, software, services, or research will be represented at SC11. So it will feel like the whole HPC world is in Seattle. And that’s the core attraction of SC – so many collaborators, prospects, potential solution providers, and contacts will there that it is hard to justify staying away.

Myth 10: The best SC11 myth of all …

To be told in person only. Find me in Seattle and I’ll tell you!

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

SC17 Student Cluster Competition Configurations: Fewer Nodes, Way More Accelerators

November 16, 2017

The final configurations for each of the SC17 “Donnybrook in Denver” Student Cluster Competition have been released. Fortunately, each team received their equipment shipments on time and undamaged, so the teams are r Read more…

By Dan Olds

Student Clusterers Demolish HPCG Record! Nanyang Sweeps Benchmarks

November 16, 2017

Nanyang pulled off the always difficult double-play at this year’s SC Student Cluster Competition. The plucky team from Singapore posted a world record LINPACK, thus taking the Highest LINPACK Award, but also managed t Read more…

By Dan Olds

Student Cluster LINPACK Record Shattered! More LINs Packed Than Ever before!

November 16, 2017

Nanyang Technological University, the pride of Singapore, utterly destroyed the Student Cluster Competition LINPACK record by posting a score of 51.77 TFlop/s at SC17 in Denver. The previous record, established by German Read more…

By Dan Olds

HPE Extreme Performance Solutions

Harness Scalable Petabyte Storage with HPE Apollo 4510 and HPE StoreEver

As a growing number of connected devices challenges IT departments to rapidly collect, manage, and store troves of data, organizations must adopt a new generation of IT to help them operate quickly and intelligently. Read more…

Hyperion Market Update: ‘Decent’ Growth Led by HPE; AI Transparency a Risk Issue

November 15, 2017

The HPC market update from Hyperion Research (formerly IDC) at the annual SC conference is a business and social “must,” and this year’s presentation at SC17 played to a SRO crowd at a downtown Denver hotel. This w Read more…

By Doug Black

Student Cluster LINPACK Record Shattered! More LINs Packed Than Ever before!

November 16, 2017

Nanyang Technological University, the pride of Singapore, utterly destroyed the Student Cluster Competition LINPACK record by posting a score of 51.77 TFlop/s a Read more…

By Dan Olds

Hyperion Market Update: ‘Decent’ Growth Led by HPE; AI Transparency a Risk Issue

November 15, 2017

The HPC market update from Hyperion Research (formerly IDC) at the annual SC conference is a business and social “must,” and this year’s presentation at S Read more…

By Doug Black

Nvidia Focuses Its Cloud Containers on HPC Applications

November 14, 2017

Having migrated its top-of-the-line datacenter GPU to the largest cloud vendors, Nvidia is touting its Volta architecture for a range of scientific computing ta Read more…

By George Leopold

HPE Launches ARM-based Apollo System for HPC, AI

November 14, 2017

HPE doubled down on its memory-driven computing vision while expanding its processor portfolio with the announcement yesterday of the company’s first ARM-base Read more…

By Doug Black

OpenACC Shines in Global Climate/Weather Codes

November 14, 2017

OpenACC, the directive-based parallel programming model used mostly for porting codes to GPUs for use on heterogeneous systems, came to SC17 touting impressive Read more…

By John Russell

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

Leading Solution Providers

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Intel Launches Software Tools to Ease FPGA Programming

September 5, 2017

Field Programmable Gate Arrays (FPGAs) have a reputation for being difficult to program, requiring expertise in specialty languages, like Verilog or VHDL. Easin Read more…

By Tiffany Trader

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

IBM Advances Web-based Quantum Programming

September 5, 2017

IBM Research is pairing its Jupyter-based Data Science Experience notebook environment with its cloud-based quantum computer, IBM Q, in hopes of encouraging a new class of entrepreneurial user to solve intractable problems that even exceed the capabilities of the best AI systems. Read more…

By Alex Woodie

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This